microsoft

    microsoft/CUAWright

    A simple SWE-style browser+desktop agent framework that achieves SOTA results on long-horizon CUA tasks

    backend
    Python
    MIT
    6.1K stars
    387 forks
    6.1K GitHub watchers
    Updated Oct 27, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    The project lists 12 contributors on GitHub.

    Use Cases & Benefits

    • Provides a minimal Python framework enabling LLMs to control browsers via code for complex, long-horizon web tasks using Playwright.
    • Enables robust, reusable, and debuggable browser automation scripts by treating the local code workspace as state instead of the browser session.
    • Use for automating multi-step web interactions like flight searches with parameterized, rerunnable Python scripts.
    • Use for integrating browser automation as a plugin skill in LLM platforms like Claude Code, OpenAI Codex, OpenClaw, and Hermes Agent.
    • Use for benchmarking and developing state-of-the-art web agents on long-horizon tasks with visual debugging and repeatable runs.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    MIT

    Permissive: commercial use, modification and redistribution are allowed with attribution.

    Community files

    • README: present
    • Code of conduct: present

    Watch-outs

    • No GitHub releases; pin a commit or tag instead of a release.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    Turn Your Coding Models to Be State-of-the-art Browser Agents

    Webwright gives LLM a terminal where it can launch multiple browser sessions to inspect the page and complete a web task. It captures and inspects page screenshots/states only when needed. It enforces each web task to be completed end-to-end within a re-runnable Python script, i.e. your web agent browsing history is a single code file. No multi-agent system, no graph engine, no plugin layer, no hidden orchestration — just a terminal, a browser, and a model.

    Already got your favorite agents, and wonder how to make Claude Code, Codex, Hermes, OpenClaw more capable in browser tasks? Consider adding Webwright plugin/skills!

    Excerpt from the microsoft/CUAWright README on GitHub (MIT license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Forks

    387+19

    Open issues

    55+10

    Compared with peers in Backend

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth

    microsoft/CUAWright compared with Backend repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    anthropics/skills187.8K+2.9K15—
    DuarteSantos8/openGym19.7K+2.4K602 days ago
    shiyu-coder/Kronos47.0K+2.3K16—
    NationalSecurityAgency/ghidra98.2K+2.3K6414 days ago
    microsoft/VibeVoice56.0K+1.1K29—
    microsoft/CUAWright6.1K—19—
    Category median56.0K+2.3K29—

    Also by microsoft

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description